CASRA+
The research proposed here is for an Arabic speech recognition application, concentrating on the Lebanese dialect. The system starts by sampling the speech, which is the process of transforming the sound from analog to digital and then extracts the features by using the Mel-Frequency Cepstral Coeffi...
محفوظ في:
| المؤلف الرئيسي: | |
|---|---|
| مؤلفون آخرون: | |
| التنسيق: | article |
| منشور في: |
2007
|
| الوصول للمادة أونلاين: | http://hdl.handle.net/10725/2320 http://dx.doi.org/10.3844/ajassp.2007.23.32 http://ku7rj9xt8c.scholar.serialssolutions.com/?sid=google&auinit=RA&aulast=Haraty&atitle=CASRA%2B:+A+colloquial+arabic+speech+recognition+application&id=doi:10.3844/ajassp.2007.23.32&title=American+journal+of+applied+sciences&volume=4&issue=1&date=2007&spage=23&issn=1546-9239 |
| الوسوم: |
إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
|
| _version_ | 1864513457921982464 |
|---|---|
| author | Haraty, Ramzi A. |
| author2 | El Ariss, Omar |
| author2_role | author |
| author_facet | Haraty, Ramzi A. El Ariss, Omar |
| author_role | author |
| dc.creator.none.fl_str_mv | Haraty, Ramzi A. El Ariss, Omar |
| dc.date.none.fl_str_mv | 2007 2015-10-23T08:19:33Z 2015-10-23T08:19:33Z 2015-10-23 |
| dc.identifier.none.fl_str_mv | 1546-9239 http://hdl.handle.net/10725/2320 http://dx.doi.org/10.3844/ajassp.2007.23.32 Haraty, R. A., & El Ariss, O. (2007). CASRA+: a colloquial Arabic speech recognition application. American Journal of Applied Sciences, 4(1), 23-32. http://ku7rj9xt8c.scholar.serialssolutions.com/?sid=google&auinit=RA&aulast=Haraty&atitle=CASRA%2B:+A+colloquial+arabic+speech+recognition+application&id=doi:10.3844/ajassp.2007.23.32&title=American+journal+of+applied+sciences&volume=4&issue=1&date=2007&spage=23&issn=1546-9239 |
| dc.language.none.fl_str_mv | en |
| dc.relation.none.fl_str_mv | American Journal of Applied Sciences |
| dc.rights.*.fl_str_mv | info:eu-repo/semantics/openAccess |
| dc.title.none.fl_str_mv | CASRA+ A Colloquial Arabic Speech Recognition Application |
| dc.type.none.fl_str_mv | Article info:eu-repo/semantics/publishedVersion info:eu-repo/semantics/article |
| description | The research proposed here is for an Arabic speech recognition application, concentrating on the Lebanese dialect. The system starts by sampling the speech, which is the process of transforming the sound from analog to digital and then extracts the features by using the Mel-Frequency Cepstral Coefficients (MFCC). The extracted features are then compared with the system's stored model; in this case the stored model chosen is a phoneme-based model. This reference model differs from the direct word template matching, where speech features that are extracted from the input are directly compared to the word templates. Each word template in the direct matching model is stored as a vector of feature parameters. Thus, when the vocabulary size of the ASR system becomes large, the memory size for the word template will become humongous. In contrast, the model used here is phoneme-like template matching. Word templates are stored as phoneme-like template parameters. Thus, the memory size for the word templates will not grow as fast as that of the direct matching model. |
| eu_rights_str_mv | openAccess |
| format | article |
| id | LAURepo_4fd564d66d58e7f82d8105fdebe9a78b |
| identifier_str_mv | 1546-9239 Haraty, R. A., & El Ariss, O. (2007). CASRA+: a colloquial Arabic speech recognition application. American Journal of Applied Sciences, 4(1), 23-32. |
| language_invalid_str_mv | en |
| network_acronym_str | LAURepo |
| network_name_str | Lebanese American University repository |
| oai_identifier_str | oai:laur.lau.edu.lb:10725/2320 |
| publishDate | 2007 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| spelling | CASRA+A Colloquial Arabic Speech Recognition ApplicationHaraty, Ramzi A.El Ariss, OmarThe research proposed here is for an Arabic speech recognition application, concentrating on the Lebanese dialect. The system starts by sampling the speech, which is the process of transforming the sound from analog to digital and then extracts the features by using the Mel-Frequency Cepstral Coefficients (MFCC). The extracted features are then compared with the system's stored model; in this case the stored model chosen is a phoneme-based model. This reference model differs from the direct word template matching, where speech features that are extracted from the input are directly compared to the word templates. Each word template in the direct matching model is stored as a vector of feature parameters. Thus, when the vocabulary size of the ASR system becomes large, the memory size for the word template will become humongous. In contrast, the model used here is phoneme-like template matching. Word templates are stored as phoneme-like template parameters. Thus, the memory size for the word templates will not grow as fast as that of the direct matching model.PublishedN/A2015-10-23T08:19:33Z2015-10-23T08:19:33Z20072015-10-23Articleinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article1546-9239http://hdl.handle.net/10725/2320http://dx.doi.org/10.3844/ajassp.2007.23.32Haraty, R. A., & El Ariss, O. (2007). CASRA+: a colloquial Arabic speech recognition application. American Journal of Applied Sciences, 4(1), 23-32.http://ku7rj9xt8c.scholar.serialssolutions.com/?sid=google&auinit=RA&aulast=Haraty&atitle=CASRA%2B:+A+colloquial+arabic+speech+recognition+application&id=doi:10.3844/ajassp.2007.23.32&title=American+journal+of+applied+sciences&volume=4&issue=1&date=2007&spage=23&issn=1546-9239enAmerican Journal of Applied Sciencesinfo:eu-repo/semantics/openAccessoai:laur.lau.edu.lb:10725/23202018-01-23T12:57:16Z |
| spellingShingle | CASRA+ Haraty, Ramzi A. |
| status_str | publishedVersion |
| title | CASRA+ |
| title_full | CASRA+ |
| title_fullStr | CASRA+ |
| title_full_unstemmed | CASRA+ |
| title_short | CASRA+ |
| title_sort | CASRA+ |
| url | http://hdl.handle.net/10725/2320 http://dx.doi.org/10.3844/ajassp.2007.23.32 http://ku7rj9xt8c.scholar.serialssolutions.com/?sid=google&auinit=RA&aulast=Haraty&atitle=CASRA%2B:+A+colloquial+arabic+speech+recognition+application&id=doi:10.3844/ajassp.2007.23.32&title=American+journal+of+applied+sciences&volume=4&issue=1&date=2007&spage=23&issn=1546-9239 |